Improving the Probabilistic Prediction Model of the Phadiatop Test by Data Pre-processing.

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F12%3A86084840" target="_blank" >RIV/61989100:27240/12:86084840 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Improving the Probabilistic Prediction Model of the Phadiatop Test by Data Pre-processing.
Original language description
The Phadiatop test was developed for screening of allergic sensitization. As the Phadiatop test is not cheap, the aim of our research is to approximately predict results of the phadiatop test by a probalistic model, which evaluates data from a personal questionnaire obtained from approximately 1 000 patients with suspected allergic diseases. Our database is based on patients who underwent examinations of the Phadiatop test at the Clinic of Occupation and Preventive Medicine, University Hospital of Ostrava, Ostrava, Czech Republic. The probabilistic prediction model has been verified on a consistent database of approximately 400 patients. Then, the second sensitivity analysis study has been performed and the prediction model has been finally simplified.As a result of the model simplification process, the final prediction model depends only on two independent variables (asthma and allergic rhinitis). The developed model is able to predict the approximate results of the Phadiatop test wi
Czech name
—
Czech description
—

Publication year
2012
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Mendel 2012 : 18th International Conference on Soft Computing : June 27-29, Brno, Czech Republic
ISBN
978-80-214-4540-6
ISSN
—
e-ISSN
—
Number of pages
5
Pages from-to
500-504
Publisher name
Vysoké učení technické v Brně
Place of publication
Brno
Event location
Brno
Event date
Jun 27, 2012
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)